sysdeps/m88k/m88110/mul_1.S

   1 ; mc88110 __mpn_mul_1 -- Multiply a limb vector with a single limb and
   2 ; store the product in a second limb vector.
   3
   4 ; Copyright (C) 1992, 1994 Free Software Foundation, Inc.
   5
   6 ; This file is part of the GNU MP Library.
   7
   8 ; The GNU MP Library is free software; you can redistribute it and/or modify
   9 ; it under the terms of the GNU General Public License as published by
  10 ; the Free Software Foundation; either version 2, or (at your option)
  11 ; any later version.
  12
  13 ; The GNU MP Library is distributed in the hope that it will be useful,
  14 ; but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 ; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16 ; GNU General Public License for more details.
  17
  18 ; You should have received a copy of the GNU General Public License
  19 ; along with the GNU MP Library; see the file COPYING.  If not, write to
  20 ; the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
  21
  22
  23 ; INPUT PARAMETERS
  24 ; res_ptr       r2
  25 ; s1_ptr        r3
  26 ; size          r4
  27 ; s2_limb       r5
  28
  29 #include "sysdep.h"
  30
  31 ENTRY (__mpn_mul_1)
  32         ld       r6,r3,0
  33         sub      r4,r0,r4
  34         sub      r3,r3,r4               ; r3 is offset s1_ptr
  35         sub      r2,r2,r4
  36         sub      r8,r2,8                ; r8 is offset res_ptr
  37         mulu.d   r10,r6,r5
  38
  39         addu     r4,r4,1
  40         bcnd     eq0,r4,Lend
  41          addu.co r2,r0,0                ; clear cy_limb
  42
  43 Loop:   ld       r6,r3[r4]
  44         addu.cio r9,r11,r2
  45         or       r2,r10,r0              ; could be avoided if unrolled
  46         addu     r4,r4,1
  47         mulu.d   r10,r6,r5
  48         bcnd     ne0,r4,Loop
  49          st      r9,r8[r4]
  50
  51 Lend:   addu.cio r9,r11,r2
  52         st       r9,r8,4
  53         jmp.n    r1
  54          addu.ci r2,r10,r0
  55
  56 ; This is the Right Way to do this on '110.  4 cycles / 64-bit limb.
  57 ;       ld.d    r10,
  58 ;       mulu.d
  59 ;       addu.cio
  60 ;       addu.cio
  61 ;       st.d
  62 ;       mulu.d  ,r11,r5
  63 ;       ld.d    r12,
  64 ;       mulu.d  ,r10,r5
  65 ;       addu.cio
  66 ;       addu.cio
  67 ;       st.d
  68 ;       mulu.d
  69 ;       ld.d    r10,
  70 ;       mulu.d
  71 ;       addu.cio
  72 ;       addu.cio
  73 ;       st.d
  74 ;       mulu.d
  75 ;       ld.d    r10,
  76 ;       mulu.d
  77 ;       addu.cio
  78 ;       addu.cio
  79 ;       st.d
  80 ;       mulu.d